Codex CLI

github.com · CLI Tool · Terminal

Codex CLI is a CLI tool: OpenAI's lightweight terminal chat interface for code operations. Its repository openai/codex carries 128,366 stars and 477 contributors, and is licensed Apache-2.0. The latest stable release is rust-v0.161.0, published 7 Oct 2026 with binaries for linux, macos, windows. npm served 25,613,321 downloads of @openai/codex in the week we read. Secrets you set for a cloud environment are removed before the agent runs, so the agent phase never sees them.

Stars: 128,366; Verified 8 Oct 2026
Last commit: 8 Oct 2026; 0 days old when we read it; Verified 8 Oct 2026
License: Apache-2.0; Verified 8 Oct 2026
Latest stable release: rust-v0.161.0; published 7 Oct 2026; Verified 8 Oct 2026
Contributors: 477; Verified 8 Oct 2026
npm downloads: 25,613,321 a week; @openai/codex; Verified 8 Oct 2026
Homebrew installs: 104,545 in 30 days; codex; Verified 8 Oct 2026
Repository: openai/codex; Rust; Verified 8 Oct 2026
Release binaries: linux, macos, windows; Verified 8 Oct 2026

Visit Codex CLI openai/codex on GitHub Codex CLI alternatives

What Codex CLI is

Codex CLI is the only agent in this set that confines itself in an OS-enforced sandbox on first run, with network access off and writes limited to the working directory.

“By default, the agent runs with network access turned off. Locally, Codex uses an OS-enforced sandbox that limits what it can touch (typically to the current workspace), plus an approval policy that controls when it must stop and ask you before acting.”

developers.openai.com/codex/sandbox

What Codex CLI costs

ChatGPT plans that include Codex run $0 for Free, $8 a month for Go, $20 a month for Plus, and from $100 a month for Pro.

“Plus · Power a few focused coding sessions each week. · $20 /month”

developers.openai.com/codex/pricing

The Business plan is $20 per user per month for 2 or more users billed annually, and $25 per user per month billed monthly.

“*2+ users, billed annually. $25 per user per month when billed monthly.”

developers.openai.com/codex/pricing

Use Codex CLI when

Point an agent at a repository you do not trust: in the default `workspace-write` mode Codex edits inside the working directory and must ask before touching anything outside it.

“Codex asks for approval to edit files outside the workspace or to run commands that require network access.”

developers.openai.com/codex/sandbox

Use a ChatGPT plan you already pay for instead of a second subscription, on Free, Go, Plus, Pro, Business, Edu or Enterprise.

“ChatGPT Work and Codex are included in your ChatGPT Free, Go, Plus, Pro, Business, Edu, or Enterprise plan”

developers.openai.com/codex/pricing

Stop a team from disabling its own guard rails: an administrator can forbid `approval_policy = "never"` and `sandbox_mode = "danger-full-access"` in a requirements file.

“requirements.toml (for example, disallowing approval_policy = "never" or”

developers.openai.com/codex/local-config

Not the right fit for

A developer who wants to run a local Ollama model should choose Crush or goose; Codex signs in with a ChatGPT account or an OpenAI API key.

“Run `codex` and select **Sign in with ChatGPT**. We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Business, Edu, or Enterprise plan.”

github.com/openai/codex

What Codex CLI is bad at

Subscription spend is unpredictable: the most-commented open issue, 630 comments since 2026-03-13, is that Codex burns the plan budget too fast, and a second reports the 5-hour budget gone in 2-3 prompts.

“Codex (gpt-5.5, Plus plan) — rate-limit cost per token jumped ~10-20x since June 16, draining the 5h budget in 2-3 prompts”

github.com/openai/codex

The agent cannot install a dependency until you edit the config, because the default sandbox keeps the network off.

“For the ChatGPT desktop app, Codex CLI, or IDE extension, the default workspace-write sandbox mode keeps network access turned off unless you enable it in your configuration:”

developers.openai.com/codex/sandbox

Windows is the weakest platform: an open issue with 106 comments reports the app freezing on Windows 11 Pro on hardware with resources to spare.

“Codex App frequently freezes/stutters on Windows 11 Pro despite sufficient system resources”

github.com/openai/codex

Security and data handling

Secrets you set for a cloud environment are removed before the agent runs, so the agent phase never sees them.

“Secrets configured for cloud environments are available only during setup and are removed before the agent phase starts.”

developers.openai.com/codex/sandbox

Technical details

Category: CLI Tool · Terminal
Repository: openai/codex
Default branch: main
Primary language: Rust
Repository created: 13 Apr 2025
Newest commit on the default branch: 8 Oct 2026
Package formats: dmg, exe, tar.gz, tar.zst, whl, zip
Architectures: arm64, x64, x86
Registries checked: npm:@openai/codex,codex-cli, homebrew:codex,codex-cli, vscode_marketplace:search(Codex CLI)
Website check: https://github.com/openai/codex answered HTTP 200

Alternatives to Codex CLI

Claude CodeCommand-line AI coding agent that understands your codebase and automates tasks via natural languageCompare
AiderAI pair programming in your terminal with clean commitsCompare
GooseLocal on-machine AI agent that allows any LLM and MCP servers as extensionsCompare
MyCoder.aiOpen source AI coding assistant with Git/GitHub integration and parallel executionCompare
RA.AidStandalone coding agent built on LangGraph's agent-based task executionCompare

All Codex CLI alternatives, ranked →

How we check this page

Machine facts. Stars, licence, the newest commit on the default branch, the latest stable release and download counts are read straight from the GitHub API and from npm, PyPI, Homebrew and the VS Code Marketplace. Each one shows the day it was last confirmed, not the day this page was built. A failed fetch keeps the old value and its old date rather than overwriting it.
Judgments. Every claim about what a tool suits, what it is bad at and what it costs is quoted from a page we read, and that page is linked beside the claim. If there is no link, we did not write the claim.
What we do not publish. No score out of five and no star rating. Every other claim here traces to a source, and a number we could not justify would undermine the ones that can.
This tool. Every claim carries the URL it came from and a verbatim quote from that URL, read on 2026-08-19.